update model card README.md

README.md

@@ -16,12 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.6117
-- Rouge1: 0.2131
-- Rouge2: 0.0981
-- Rougel: 0.1763
-- Rougelsum: 0.1737
-- Gen Len: 18.95
+- Loss: 2.1099
+- Rouge1: 0.398
+- Rouge2: 0.2035
+- Rougel: 0.3373
+- Rougelsum: 0.3373
+- Gen Len: 17.8606
 
 ## Model description
 
@@ -51,12 +51,12 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 5    | 3.7385          | 0.2228 | 0.1074 | 0.187  | 0.1833    | 18.95   |
-| No log        | 2.0   | 10   | 3.6693          | 0.2172 | 0.0977 | 0.1805 | 0.1771    | 18.95   |
-| No log        | 3.0   | 15   | 3.6294          | 0.2179 | 0.0981 | 0.1809 | 0.1775    | 18.95   |
-| No log        | 4.0   | 20   | 3.6117          | 0.2131 | 0.0981 | 0.1763 | 0.1737    | 18.95   |
+| Training Loss | Epoch | Step  | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| 2.4288        | 1.0   | 2500  | 2.1944          | 0.3895 | 0.1972 | 0.3304 | 0.3303    | 17.8459 |
+| 2.3376        | 2.0   | 5000  | 2.1381          | 0.3948 | 0.2012 | 0.3347 | 0.3347    | 17.8277 |
+| 2.2978        | 3.0   | 7500  | 2.1155          | 0.3972 | 0.2027 | 0.3365 | 0.3366    | 17.8694 |
+| 2.3072        | 4.0   | 10000 | 2.1099          | 0.398  | 0.2035 | 0.3373 | 0.3373    | 17.8606 |
 
 
 ### Framework versions